AntiSMI

AntiSMI News API

The news API from AntiSMI — 5 operation(s) for news.

GitHub OpenAPI

Operations 5

GET /news/{news_id} Get News By Id #
POST /news/search Search News #
POST /news/similarity_search Similarity Search #
POST /news/vector_search Vector Search #
POST /news/topic_timeline Topic Timeline #

Specifications

⚙
OpenAPI
https://artifacts.apis.io/antismi-media/openapi/antismi-media-news-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://artifacts.apis.io/antismi-media/json-schema/antismi-media-digest-request-schema.json
📊
JSONSchema
https://artifacts.apis.io/antismi-media/json-schema/antismi-media-word-cloud-request-schema.json
📊
JSONSchema
https://artifacts.apis.io/antismi-media/json-schema/antismi-media-topic-timeline-request-schema.json
📊
JSONSchema
https://artifacts.apis.io/antismi-media/json-schema/antismi-media-agency-db-schema.json
📊
JSONSchema
https://artifacts.apis.io/antismi-media/json-schema/antismi-media-historical-digest-request-schema.json
📊
JSONSchema
https://artifacts.apis.io/antismi-media/json-schema/antismi-media-trends-request-schema.json

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/antismi-media:antismi-media-news-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

antismi-media-news-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Russian Archive News API
  description: 'Semantic search, daily digests and trends over a Russian-language news archive since 1999. Authentication: X-API-Key header (get a key at https://news.antismi.media, Settings → Account). Plans and limits: https://news.antismi.media/mcp'
  version: 1.0.0
tags:
- name: News
paths:
  /news/{news_id}:
    get:
      tags:
      - News
      summary: Get News By Id
      description: Get full news article by ID with metadata
      operationId: get_news_by_id_news__news_id__get
      parameters:
      - name: news_id
        in: path
        required: true
        schema:
          type: integer
          title: News Id
      - name: lang
        in: query
        required: false
        schema:
          enum:
          - ru
          - en
          type: string
          description: 'Язык метаданных: en → title/resume/key_notions из *_en с fallback на русский'
          default: ru
          title: Lang
        description: 'Язык метаданных: en → title/resume/key_notions из *_en с fallback на русский'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /news/search:
    post:
      tags:
      - News
      summary: Search News
      description: 'Search news with filters


        Available only for premium users.'
      operationId: search_news_news_search_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/NewsFilter'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NewsSearchResult'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - APIKeyHeader: []
  /news/similarity_search:
    post:
      tags:
      - News
      summary: Similarity Search
      description: 'Perform similarity search using embeddings


        Available only for premium users.'
      operationId: similarity_search_news_similarity_search_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SimilaritySearch'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SimilaritySearchResult'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - APIKeyHeader: []
  /news/vector_search:
    post:
      tags:
      - News
      summary: Vector Search
      description: 'Perform vector search using text query


        This endpoint:

        1. Generates embedding from the query text using Google Gemini API

        2. Searches for similar news using pgvector (cosine similarity)

        3. Returns enriched news items sorted by relevance


        Available only for premium users.


        Parameters:

        - query: Search text (will be converted to embedding)

        - date_from: Optional start date filter

        - date_to: Optional end date filter

        - limit: Maximum number of results (default 50, max 100)

        - telegram_id: Optional user ID for logging'
      operationId: vector_search_news_vector_search_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VectorSearchRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VectorSearchResult'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - APIKeyHeader: []
  /news/topic_timeline:
    post:
      tags:
      - News
      summary: Topic Timeline
      description: 'Хронология темы: сколько из K ближайших по смыслу новостей приходится на каждый период

        (год или месяц), нормировка на объём базы за период, лучшие заголовки периода с точной похожестью.


        Для вопросов «как менялась тема за N лет»: обычный vector_search отдаёт лишь top-N ближайших,

        что не показывает динамику. Только premium/media/system, как и vector_search.'
      operationId: topic_timeline_news_topic_timeline_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TopicTimelineRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TopicTimelineResult'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - APIKeyHeader: []
components:
  schemas:
    TopicTimelineResult:
      properties:
        query:
          type: string
          title: Query
        step:
          type: string
          title: Step
        date_from:
          type: string
          format: date-time
          title: Date From
        date_to:
          type: string
          format: date-time
          title: Date To
        candidates:
          type: integer
          title: Candidates
        min_similarity:
          type: number
          title: Min Similarity
        periods:
          items:
            $ref: '#/components/schemas/TopicTimelinePeriod'
          type: array
          title: Periods
        search_time_ms:
          anyOf:
          - type: number
          - type: 'null'
          title: Search Time Ms
      type: object
      required:
      - query
      - step
      - date_from
      - date_to
      - candidates
      - min_similarity
      - periods
      title: TopicTimelineResult
      description: Ответ хронологии темы.
    SimilaritySearchResult:
      properties:
        items:
          items:
            type: object
          type: array
          title: Items
      type: object
      required:
      - items
      title: SimilaritySearchResult
      description: Result of similarity search
      example:
        items:
        - news:
            id: 1
            similarity_score: 0.95
            title: Example news
    SentimentEnum:
      type: string
      enum:
      - positive
      - neutral
      - negative
      title: SentimentEnum
      description: Sentiment classification
    TopicTimelineRequest:
      properties:
        query:
          type: string
          maxLength: 1000
          minLength: 1
          title: Query
          description: Тема на естественном языке
        date_from:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Date From
          description: Начало периода (по умолчанию 1999-01-01)
        date_to:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Date To
          description: Конец периода (по умолчанию сейчас)
        step:
          anyOf:
          - type: string
            enum:
            - year
            - month
          - type: 'null'
          title: Step
          description: Шаг периода; по умолчанию year при окне > 3 лет, иначе month
        candidates:
          type: integer
          maximum: 2000.0
          minimum: 100.0
          title: Candidates
          description: Сколько ближайших новостей распределять по периодам
          default: 2000
        per_period:
          type: integer
          maximum: 10.0
          minimum: 1.0
          title: Per Period
          description: Сколько заголовков отдавать на период
          default: 5
        min_similarity:
          type: number
          maximum: 1.0
          minimum: 0.0
          title: Min Similarity
          description: Порог косинусной похожести для заголовков
          default: 0.5
        telegram_id:
          anyOf:
          - type: integer
          - type: 'null'
          title: Telegram Id
          description: Telegram user ID для логирования
        lang:
          type: string
          enum:
          - ru
          - en
          title: Lang
          description: Язык заголовков и понятий в ответе (en — из *_en с fallback на русский)
          default: ru
      type: object
      required:
      - query
      title: TopicTimelineRequest
      description: 'Запрос хронологии темы: как менялось внимание к теме по периодам (годам или месяцам).'
    NewsEnriched:
      properties:
        id:
          type: integer
          title: Id
        url:
          type: string
          title: Url
        news_text:
          type: string
          title: News Text
        news_date:
          type: string
          format: date-time
          title: News Date
        links:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Links
        agency_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Agency Name
        media_type:
          anyOf:
          - type: string
          - type: 'null'
          title: Media Type
        category:
          anyOf:
          - type: string
          - type: 'null'
          title: Category
        category_title:
          anyOf:
          - type: string
          - type: 'null'
          title: Category Title
        category_emoji:
          anyOf:
          - type: string
          - type: 'null'
          title: Category Emoji
        title:
          anyOf:
          - type: string
          - type: 'null'
          title: Title
        resume:
          anyOf:
          - type: string
          - type: 'null'
          title: Resume
        key_notions:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Key Notions
        sentiment:
          anyOf:
          - $ref: '#/components/schemas/SentimentEnum'
          - type: 'null'
        meta_lang_source:
          anyOf:
          - type: string
          - type: 'null'
          title: Meta Lang Source
      type: object
      required:
      - id
      - url
      - news_text
      - news_date
      title: NewsEnriched
      description: Complete enriched news (response model)
    NewsFilter:
      properties:
        start_date:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Start Date
        end_date:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: End Date
        agency_ids:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Agency Ids
        category_ids:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Category Ids
        media_types:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Media Types
        sentiments:
          anyOf:
          - items:
              $ref: '#/components/schemas/SentimentEnum'
            type: array
          - type: 'null'
          title: Sentiments
        limit:
          type: integer
          maximum: 1000.0
          title: Limit
          default: 100
        offset:
          type: integer
          minimum: 0.0
          title: Offset
          default: 0
        lang:
          type: string
          enum:
          - ru
          - en
          title: Lang
          description: 'Язык метаданных: en → title/resume/key_notions из *_en с fallback на русский'
          default: ru
      type: object
      title: NewsFilter
      description: Model for filtering news
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    TopicTimelineItem:
      properties:
        id:
          type: integer
          title: Id
        news_date:
          type: string
          format: date-time
          title: News Date
        title:
          anyOf:
          - type: string
          - type: 'null'
          title: Title
        url:
          type: string
          title: Url
        agency_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Agency Name
        similarity:
          type: number
          title: Similarity
      type: object
      required:
      - id
      - news_date
      - url
      - similarity
      title: TopicTimelineItem
      description: Заголовок периода с точной похожестью.
    SimilaritySearch:
      properties:
        query_embedding:
          items:
            type: number
          type: array
          maxItems: 768
          minItems: 768
          title: Query Embedding
        limit:
          type: integer
          maximum: 100.0
          title: Limit
          default: 10
        similarity_threshold:
          type: number
          maximum: 1.0
          minimum: 0.0
          title: Similarity Threshold
          default: 0.7
        filters:
          anyOf:
          - $ref: '#/components/schemas/NewsFilter'
          - type: 'null'
      type: object
      required:
      - query_embedding
      title: SimilaritySearch
      description: Model for similarity search
    VectorSearchResult:
      properties:
        news:
          items:
            $ref: '#/components/schemas/NewsEnriched'
          type: array
          title: News
        total_count:
          type: integer
          title: Total Count
        query_embedding_generated:
          type: boolean
          title: Query Embedding Generated
          default: true
        search_time_ms:
          anyOf:
          - type: number
          - type: 'null'
          title: Search Time Ms
      type: object
      required:
      - news
      - total_count
      title: VectorSearchResult
      description: Response model for vector search
    NewsSearchResult:
      properties:
        total_count:
          type: integer
          title: Total Count
        items:
          items:
            $ref: '#/components/schemas/NewsEnriched'
          type: array
          title: Items
        has_more:
          type: boolean
          title: Has More
      type: object
      required:
      - total_count
      - items
      - has_more
      title: NewsSearchResult
      description: Result of news search
    TopicTimelinePeriod:
      properties:
        period:
          type: string
          title: Period
          description: '''2016'' или ''2016-03'''
        candidates:
          type: integer
          title: Candidates
          description: Сколько из K ближайших новостей попало в период
        corpus_total:
          anyOf:
          - type: integer
          - type: 'null'
          title: Corpus Total
          description: Всего новостей в базе за период (оценка)
        per_10k:
          anyOf:
          - type: number
          - type: 'null'
          title: Per 10K
          description: candidates на 10 000 новостей базы за период
        best_similarity:
          anyOf:
          - type: number
          - type: 'null'
          title: Best Similarity
          description: Лучшая точная похожесть в периоде
        top:
          items:
            $ref: '#/components/schemas/TopicTimelineItem'
          type: array
          title: Top
          default: []
        notions:
          items:
            type: string
          type: array
          title: Notions
          default: []
      type: object
      required:
      - period
      - candidates
      title: TopicTimelinePeriod
      description: Один период хронологии.
    VectorSearchRequest:
      properties:
        query:
          type: string
          maxLength: 1000
          minLength: 1
          title: Query
          description: Search query text
        date_from:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Date From
          description: Start date filter
        date_to:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Date To
          description: End date filter
        limit:
          type: integer
          maximum: 100.0
          title: Limit
          description: Maximum number of results
          default: 50
        telegram_id:
          anyOf:
          - type: integer
          - type: 'null'
          title: Telegram Id
          description: Telegram user ID for logging
        lang:
          type: string
          enum:
          - ru
          - en
          title: Lang
          description: 'Язык метаданных в ответе: ru (по умолчанию) или en (title/resume/key_notions из *_en, fallback на русский)'
          default: ru
      type: object
      required:
      - query
      title: VectorSearchRequest
      description: Request model for vector search with text query
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key